{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:SQBX47BNFC32K4TS47UDLPTB6P","short_pith_number":"pith:SQBX47BN","canonical_record":{"source":{"id":"1810.12125","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-29T13:47:52Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"e0f44660b3c1c96a97b9101cac31f504ba6bfa54041ab4a1fca54f6c91aaa9fa","abstract_canon_sha256":"0e4eb707aa39f4ae8684e11842d0dd342476bcecd0d8bb987bb8689e67b55a15"},"schema_version":"1.0"},"canonical_sha256":"94037e7c2d28b7a57272e7e835be61f3ea45eee5173cd91c18657e8270f00ecf","source":{"kind":"arxiv","id":"1810.12125","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12125","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12125v4","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12125","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"pith_short_12","alias_value":"SQBX47BNFC32","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SQBX47BNFC32K4TS","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SQBX47BN","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:SQBX47BNFC32K4TS47UDLPTB6P","target":"record","payload":{"canonical_record":{"source":{"id":"1810.12125","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-29T13:47:52Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"e0f44660b3c1c96a97b9101cac31f504ba6bfa54041ab4a1fca54f6c91aaa9fa","abstract_canon_sha256":"0e4eb707aa39f4ae8684e11842d0dd342476bcecd0d8bb987bb8689e67b55a15"},"schema_version":"1.0"},"canonical_sha256":"94037e7c2d28b7a57272e7e835be61f3ea45eee5173cd91c18657e8270f00ecf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:23.533716Z","signature_b64":"SSX2a5dPv3X4t8pZ6Qtpdi2SYt65KQO1Ag4XAueJKdJ5C0OuI8ekXbNlYqaSeAsERQRlTdPuJaTqhUjI2q37Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94037e7c2d28b7a57272e7e835be61f3ea45eee5173cd91c18657e8270f00ecf","last_reissued_at":"2026-05-17T23:43:23.532993Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:23.532993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.12125","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b8Fg+oByjuTeQE+leiqw2fm2iVB/2fW/m3nSHjY/pnl2nNEGUjnRXJDvy0XzmDKStsaynWwtafHT0I6Bq32hDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:27:30.793513Z"},"content_sha256":"a3d21bd5dbd044a1d939e90013c53351e5e7757a7ccf59df06076cccf0d81df2","schema_version":"1.0","event_id":"sha256:a3d21bd5dbd044a1d939e90013c53351e5e7757a7ccf59df06076cccf0d81df2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:SQBX47BNFC32K4TS47UDLPTB6P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gradual Machine Learning for Entity Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.DB","authors_text":"Boyi Hou, Qun Chen, Yanyan Wang, Youcef Nafa, Zhanhuai Li","submitted_at":"2018-10-29T13:47:52Z","abstract_excerpt":"Usually considered as a classification problem, entity resolution (ER) can be very challenging on real data due to the prevalence of dirty values. The state-of-the-art solutions for ER were built on a variety of learning models (most notably deep neural networks), which require lots of accurately labeled training data. Unfortunately, high-quality labeled data usually require expensive manual work, and are therefore not readily available in many real scenarios. In this paper, we propose a novel learning paradigm for ER, called gradual machine learning, which aims to enable effective machine lab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12125","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yVvOzK8+S4P9ujWdVUBn6SINlRozdvgju1/aZ/CpKixdDGvrHQgLYTYZcQKZr1GdWOqvxCp1eQdSITCFLZu9Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:27:30.794336Z"},"content_sha256":"9af23cfea8e87ebf663fdf248b4f662b46fae6bcdd9e9619122b93cccae01740","schema_version":"1.0","event_id":"sha256:9af23cfea8e87ebf663fdf248b4f662b46fae6bcdd9e9619122b93cccae01740"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SQBX47BNFC32K4TS47UDLPTB6P/bundle.json","state_url":"https://pith.science/pith/SQBX47BNFC32K4TS47UDLPTB6P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SQBX47BNFC32K4TS47UDLPTB6P/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T11:27:30Z","links":{"resolver":"https://pith.science/pith/SQBX47BNFC32K4TS47UDLPTB6P","bundle":"https://pith.science/pith/SQBX47BNFC32K4TS47UDLPTB6P/bundle.json","state":"https://pith.science/pith/SQBX47BNFC32K4TS47UDLPTB6P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SQBX47BNFC32K4TS47UDLPTB6P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:SQBX47BNFC32K4TS47UDLPTB6P","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0e4eb707aa39f4ae8684e11842d0dd342476bcecd0d8bb987bb8689e67b55a15","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-29T13:47:52Z","title_canon_sha256":"e0f44660b3c1c96a97b9101cac31f504ba6bfa54041ab4a1fca54f6c91aaa9fa"},"schema_version":"1.0","source":{"id":"1810.12125","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12125","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12125v4","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12125","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"pith_short_12","alias_value":"SQBX47BNFC32","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SQBX47BNFC32K4TS","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SQBX47BN","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:9af23cfea8e87ebf663fdf248b4f662b46fae6bcdd9e9619122b93cccae01740","target":"graph","created_at":"2026-05-17T23:43:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Usually considered as a classification problem, entity resolution (ER) can be very challenging on real data due to the prevalence of dirty values. The state-of-the-art solutions for ER were built on a variety of learning models (most notably deep neural networks), which require lots of accurately labeled training data. Unfortunately, high-quality labeled data usually require expensive manual work, and are therefore not readily available in many real scenarios. In this paper, we propose a novel learning paradigm for ER, called gradual machine learning, which aims to enable effective machine lab","authors_text":"Boyi Hou, Qun Chen, Yanyan Wang, Youcef Nafa, Zhanhuai Li","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-29T13:47:52Z","title":"Gradual Machine Learning for Entity Resolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12125","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a3d21bd5dbd044a1d939e90013c53351e5e7757a7ccf59df06076cccf0d81df2","target":"record","created_at":"2026-05-17T23:43:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0e4eb707aa39f4ae8684e11842d0dd342476bcecd0d8bb987bb8689e67b55a15","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-29T13:47:52Z","title_canon_sha256":"e0f44660b3c1c96a97b9101cac31f504ba6bfa54041ab4a1fca54f6c91aaa9fa"},"schema_version":"1.0","source":{"id":"1810.12125","kind":"arxiv","version":4}},"canonical_sha256":"94037e7c2d28b7a57272e7e835be61f3ea45eee5173cd91c18657e8270f00ecf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94037e7c2d28b7a57272e7e835be61f3ea45eee5173cd91c18657e8270f00ecf","first_computed_at":"2026-05-17T23:43:23.532993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:23.532993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SSX2a5dPv3X4t8pZ6Qtpdi2SYt65KQO1Ag4XAueJKdJ5C0OuI8ekXbNlYqaSeAsERQRlTdPuJaTqhUjI2q37Bw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:23.533716Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.12125","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3d21bd5dbd044a1d939e90013c53351e5e7757a7ccf59df06076cccf0d81df2","sha256:9af23cfea8e87ebf663fdf248b4f662b46fae6bcdd9e9619122b93cccae01740"],"state_sha256":"cbec84c176fcaa510e8622e62a6301cbfb0d3dbb72782dc2828fff3ad4611005"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QMYUhr0B6al3nsaqDfBRyeJHP1vscYIkyAG3QnnJafMGh0cukd5eXW7UMhQfz/Cc8GAquFPJsPmutW87br8GBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T11:27:30.797822Z","bundle_sha256":"c059cc25a3682164e7eef202345725119e267e10f41354c9cd94a9e8b1d979b9"}}